terraform-provider-stackgen

sg_guild_model_provider (Resource)

⚠️ Experimental — This resource is part of the Guild platform and may change in future releases.

Manages a named LLM model provider configuration. Providers hold connection details (type, host, token reference) that models are registered against.

Example Usage

# Register an LLM provider other workloads resolve models against.
resource "sg_guild_model_provider" "example" {
  name            = "openai-shared"
  provider_type   = "openai"
  host            = "https://api.openai.com/v1"
  token_reference = "openai-api-key"
  # Optional: TENANT, PROJECT, or USER — integration scope for this provider.
  scope = "TENANT"
}

Import

Import an existing sg_guild_model_provider using its model provider name:

terraform import sg_guild_model_provider.example 'openai-prod'

Schema

Required

• name (String) Unique provider name (e.g. openai-prod). Changing forces replacement.
• provider_type (String) LLM provider type (e.g. openai or anthropic or gemini).

Optional

• host (String) Custom API endpoint URL (for self-hosted or proxy endpoints).
• scope (String) Integration scope for this provider: TENANT PROJECT or USER. When unset on create the Guild API default applies.
• token_reference (String) Name of a registered token reference (secret) that holds the API key.